Twitter Search Skill logo

Twitter Search Skill

Community
zeenie-ai
twitter-search-skill

Search for recent tweets on Twitter/X using keywords, hashtags, mentions, and advanced query operators. Returns rich tweet data with expanded URLs, author info, media, metrics, and referenced tweets.

Overview

Publisherzeenie-ai
RepositoryOpenCompany
Skill nametwitter-search-skill
Stars
912
Forks
137
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by zeenie-ai on GitHub. Read the source before you install it.

Installation

Install the Twitter Search Skill AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/zeenie-ai/OpenCompany.git /tmp/OpenCompany
mkdir -p .claude/skills
cp -r /tmp/OpenCompany/server/skills/social_agent/twitter-search-skill .claude/skills/twitter-search-skill
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Twitter Search Skill in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Twitter Search Skill on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Twitter Search Skill is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Twitter Search Tool

Search for recent tweets on Twitter/X with rich data including full text, expanded URLs, author profiles, media attachments, engagement metrics, and referenced tweets.

How It Works

This skill provides instructions for the Twitter Search tool node. Connect the Twitter Search node to an AI Agent's input-tools handle to enable tweet searching.

twitter_search Tool

Search for tweets matching a query. Returns enriched tweet data via X API v2 expansions.

Schema Fields

FieldTypeRequiredDescription
querystringYesSearch query (supports operators)
max_resultsintegerNoNumber of results (10-100, default: 10)

Query Rules (X API constraint — required reading)

Every query must contain at least one STANDALONE term. Operator-only queries return HTTP 400 from X.

  • Standalone (can stand alone as the whole query): keyword, "quoted phrase", #hashtag, @mention, from:user, to:user, url:domain, context:.
  • Conjunction-required (must be combined with a standalone term): lang:, is:retweet / -is:retweet, is:reply / -is:reply, is:quote, has:links, has:media, has:images, has:videos, plain -negation of any keyword.

HTTP 400 — these queries fail:

Bad queryWhy
lang:enconjunction-required operator alone
-is:retweetnegation alone
-is:retweet lang:entwo conjunction-required operators, zero standalone
has:mediaconjunction-required alone
is:replyconjunction-required alone

Valid — these have at least one standalone term:

Good queryStandalone anchor
python -is:retweetkeyword python
"machine learning" lang:enquoted phrase
from:elonmusk -is:retweetfrom:
#ai has:mediahashtag
@OpenAI lang:enmention
url:"github.com" -is:retweeturl:

Query Operators

The X API v2 supports advanced search operators:

OperatorExampleDescription
keywordpythonTweets containing the word
phrase"machine learning"Exact phrase match
hashtag#AITweets with hashtag
mention@usernameTweets mentioning user
fromfrom:elonmuskTweets by specific user
toto:usernameReplies to user
-keyword-spamExclude keyword
ORpython OR javascriptEither term
langlang:enLanguage filter
has:linksAI has:linksTweets with URLs
has:mediasunset has:mediaTweets with media
has:imagescat has:imagesTweets with images
has:videosnews has:videosTweets with videos
is:retweetbitcoin is:retweetOnly retweets
-is:retweetnews -is:retweetExclude retweets
is:reply@user is:replyOnly replies
-is:replytopic -is:replyExclude replies
is:quotebreaking is:quoteOnly quote tweets
url:url:"github.com"Tweets linking to domain
context:context:131.1007360414114435072Tweets in topic context

Examples

Simple keyword search:

json
{
  "query": "artificial intelligence",
  "max_results": 20
}

Search with hashtag:

json
{
  "query": "#MachineLearning -is:retweet lang:en",
  "max_results": 50
}

Search tweets from a user (original tweets only):

json
{
  "query": "from:OpenAI -is:retweet",
  "max_results": 10
}

Complex query:

json
{
  "query": "AI (startup OR company) -is:retweet lang:en has:links",
  "max_results": 100
}

Search for media posts:

json
{
  "query": "sunset has:media -is:retweet",
  "max_results": 25
}

Response Format

Each tweet includes rich data. The display_text field has t.co links replaced with full expanded URLs. Long-form tweets (>280 chars) use note_tweet content.

json
{
  "success": true,
  "result": {
    "tweets": [
      {
        "id": "1234567890123456789",
        "text": "Check out https://t.co/abc123",
        "display_text": "Check out https://www.example.com/full-article-url",
        "author_id": "987654321",
        "created_at": "2025-02-19T10:30:00+00:00",
        "lang": "en",
        "source": "Twitter Web App",
        "conversation_id": "1234567890123456789",
        "in_reply_to_user_id": null,
        "possibly_sensitive": false,
        "public_metrics": {
          "retweet_count": 42,
          "reply_count": 12,
          "like_count": 256,
          "quote_count": 5,
          "bookmark_count": 18,
          "impression_count": 15000
        },
        "author": {
          "id": "987654321",
          "username": "techuser",
          "name": "Tech User",
          "profile_image_url": "https://pbs.twimg.com/..."
        },
        "urls": [
          {
            "url": "https://t.co/abc123",
            "expanded_url": "https://www.example.com/full-article-url",
            "display_url": "example.com/full-article-..."
          }
        ],
        "media": [
          {
            "media_key": "3_123456789",
            "type": "photo",
            "url": "https://pbs.twimg.com/media/...",
            "alt_text": "Description of the image"
          }
        ],
        "referenced_tweets": [
          {
            "type": "quoted",
            "id": "1111111111111111111",
            "text": "Original tweet text that was quoted",
            "author_id": "222222222"
          }
        ]
      }
    ],
    "count": 20,
    "query": "#AI"
  },
  "execution_time": 0.82
}

Key Response Fields

FieldDescription
textRaw tweet text (may contain t.co shortened links)
display_textText with t.co links expanded to full URLs -- use this for display
authorAuthor profile (username, name, profile image) from includes expansion
public_metricsEngagement: retweet_count, reply_count, like_count, quote_count, bookmark_count, impression_count
mediaAttached media objects (photo, video, animated_gif) with URLs and alt text
urlsExpanded URL mappings (short t.co -> full URL)
referenced_tweetsQuoted or replied-to tweets with their text content
langDetected language code (e.g., "en", "es", "ja")
sourceClient used to post (e.g., "Twitter Web App", "Twitter for iPhone")
conversation_idID of the conversation thread
in_reply_to_user_idIf a reply, the user ID being replied to

Important Notes

  • Always use display_text instead of text when showing tweet content to users -- it contains expanded URLs
  • Long tweets: Tweets over 280 characters use note_tweet; the full text is in the text field
  • Media URLs: media[].url gives the direct image/video URL
  • Referenced tweets: referenced_tweets[].text contains the full text of quoted/replied tweets
  • Metrics: public_metrics shows real-time engagement counts

Error Response

json
{
  "success": false,
  "error": "Search query is required",
  "execution_time": 0.01
}

Guidelines

  1. Always include a standalone term (keyword / phrase / hashtag / mention / from: / to: / url:) — see "Query Rules" above. Operator-only queries fail with HTTP 400.
  2. Max results: Minimum 10, maximum 100 per request (X API v2 constraint).
  3. Recent tweets only: X API v2 free/basic tier searches recent tweets (last 7 days).
  4. Rate limits: Be mindful of API rate limits when searching repeatedly.
  5. Combine operators on a base term: e.g., python -is:retweet lang:en has:links — the python keyword anchors all three filters.
  6. Exclude retweets: append -is:retweet to a keyword query (e.g. python -is:retweet). Cannot stand alone.
  7. Language filter: append lang:en to a keyword/from:/hashtag query (e.g. "openai" lang:en). Cannot stand alone.
  8. Media filter: append has:media / has:images / has:videos to a keyword query. Cannot stand alone.

Common Use Cases

  • Monitor brand mentions with engagement metrics
  • Track trending topics and measure reach
  • Find tweets about specific subjects with media
  • Research competitor activity and engagement
  • Gather content for curation with full context
  • Find influencers by analyzing follower/engagement metrics
  • Analyze conversation threads via conversation_id

Setup Requirements

  1. Connect the Twitter Search node to an AI Agent's input-tools handle
  2. Ensure Twitter is connected (authenticated via OAuth in Credentials Modal)
  3. Your X Developer account must have appropriate API access level

References

Frequently asked questions

What does the Twitter Search Skill AI skill do?

Search for recent tweets on Twitter/X using keywords, hashtags, mentions, and advanced query operators. Returns rich tweet data with expanded URLs, author info, media, metrics, and referenced tweets.

Why use Twitter Search Skill on TypingMind?

Because you install it once and use it with any model. Twitter Search Skill is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Twitter Search Skill in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/zeenie-ai/OpenCompany/tree/main/server/skills/social_agent/twitter-search-skill. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Twitter Search Skill?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Twitter Search Skill?

As many as you like. As long as a model supports skills, you can use Twitter Search Skill with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Twitter Search Skill AI skill free?

Yes. It is published on GitHub by zeenie-ai under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇